© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45699
    Prev
    Next
    INDEX
    Explanations

    hands, fingers, wrists, arms, gloves

    np_acts-logits-general · gemini-2.5-flash-lite

    hands and gloves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setCode
    0.49
    ध्यात्म
    0.45
    ᱣ
    0.44
     stools
    0.44
     debugShow
    0.43
    तह
    0.43
    声
    0.43
     stool
    0.42
    NewUrl
    0.42
    㡷
    0.42
    POSITIVE LOGITS
     Gloves
    1.13
     glove
    1.09
     Fingers
    1.06
     gloves
    1.05
     fingers
    1.05
     Glove
    1.02
     tangan
    1.01
     Hands
    1.00
     wrists
    1.00
     Wrist
    0.99
    Activations Density 0.138%

    No Known Activations